© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128778
    Prev
    Next
    INDEX
    Explanations

    include statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ப்பதற்கு
    -0.07
     If
    -0.07
    ভাগে
    -0.06
     simplemente
    -0.06
     of
    -0.06
     there
    -0.06
     commonly
    -0.06
    ాలంటే
    -0.06
     if
    -0.06
     There
    -0.06
    POSITIVE LOGITS
    它的
    0.07
     its
    0.06
     அதன்
    0.06
    Its
    0.06
    その
    0.06
     এর
    0.06
     mainu
    0.06
     ـ
    0.06
    其
    0.06
     ploy
    0.05
    Activations Density 0.004%

    No Known Activations